End of training

README.md

@@ -18,18 +18,18 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [hfl/chinese-macbert-base](https://huggingface.co/hfl/chinese-macbert-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4276
-- Accuracy: 0.7110
-- F1 Macro: 0.6575
-- Low Precision: 0.3970
-- Low Recall: 0.6328
-- Low F1: 0.4879
-- Medium Precision: 0.8236
-- Medium Recall: 0.6441
-- Medium F1: 0.7229
-- High Precision: 0.7005
-- High Recall: 0.8349
-- High F1: 0.7618
+- Loss: 2.4903
+- Accuracy: 0.7699
+- F1 Macro: 0.6888
+- Low Precision: 0.6247
+- Low Recall: 0.4030
+- Low F1: 0.4899
+- Medium Precision: 0.7837
+- Medium Recall: 0.8259
+- Medium F1: 0.8042
+- High Precision: 0.7706
+- High Recall: 0.7740
+- High F1: 0.7723
 
 ## Model description
 
@@ -60,11 +60,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Low Precision | Low Recall | Low F1 | Medium Precision | Medium Recall | Medium F1 | High Precision | High Recall | High F1 |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-------------:|:----------:|:------:|:----------------:|:-------------:|:---------:|:--------------:|:-----------:|:-------:|
-| 0.2859        | 1.0   | 1590 | 0.2949          | 0.6352   | 0.5889   | 0.2921        | 0.6930     | 0.4110 | 0.8139           | 0.4930        | 0.6140    | 0.6620         | 0.8427      | 0.7415  |
-| 0.3450        | 2.0   | 3180 | 0.2713          | 0.6566   | 0.6111   | 0.2905        | 0.7536     | 0.4193 | 0.8145           | 0.5486        | 0.6556    | 0.7203         | 0.8009      | 0.7585  |
-| 0.1936        | 3.0   | 4770 | 0.2918          | 0.6822   | 0.6336   | 0.3331        | 0.7152     | 0.4545 | 0.8204           | 0.5901        | 0.6865    | 0.7099         | 0.8176      | 0.7599  |
-| 0.2278        | 4.0   | 6360 | 0.3409          | 0.6833   | 0.6350   | 0.3521        | 0.6943     | 0.4673 | 0.8445           | 0.5686        | 0.6796    | 0.6780         | 0.8594      | 0.7580  |
-| 0.1516        | 5.0   | 7950 | 0.4276          | 0.7110   | 0.6575   | 0.3970        | 0.6328     | 0.4879 | 0.8236           | 0.6441        | 0.7229    | 0.7005         | 0.8349      | 0.7618  |
+| 2.2603        | 1.0   | 1590 | 2.3939          | 0.7494   | 0.6085   | 0.6964        | 0.1771     | 0.2823 | 0.7452           | 0.8456        | 0.7922    | 0.7604         | 0.7419      | 0.7510  |
+| 2.3054        | 2.0   | 3180 | 2.2652          | 0.7657   | 0.6696   | 0.6445        | 0.3345     | 0.4404 | 0.7669           | 0.8450        | 0.8040    | 0.7799         | 0.7494      | 0.7643  |
+| 1.7666        | 3.0   | 4770 | 2.3074          | 0.7663   | 0.6847   | 0.6148        | 0.3995     | 0.4843 | 0.7821           | 0.8202        | 0.8007    | 0.7649         | 0.7736      | 0.7692  |
+| 1.7766        | 4.0   | 6360 | 2.3694          | 0.7670   | 0.6888   | 0.5959        | 0.4200     | 0.4927 | 0.7901           | 0.8082        | 0.7990    | 0.7604         | 0.7893      | 0.7746  |
+| 1.4851        | 5.0   | 7950 | 2.4903          | 0.7699   | 0.6888   | 0.6247        | 0.4030     | 0.4899 | 0.7837           | 0.8259        | 0.8042    | 0.7706         | 0.7740      | 0.7723  |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68bca36f777eebea318161ef0cdde2e416991ad1d8f5e737e68b07d9e32c46f4
+oid sha256:dcdfd613dbcdd397d06b821dc31704aca15bdbdd632c264cdf675bb07f625784
 size 409103292